文献速递妇产影像腹部技术与安全MR

多参数MRI影像组学可解释模型预测子宫内膜癌淋巴血管间隙侵犯

Multiparametric MRI Radiomics-Based Interpretable Machine Learning Model for the Prediction of Lymphovascular Space Invasion in Endometrial Cancer.
PubMed 文献 · Acad Radiol · 2026-07-20

本研究回顾性纳入两中心408例子宫内膜癌患者,提取瘤内及瘤周影像组学特征并联合CA125与肿瘤直径,比较六种机器学习算法。NeuralNetwork模型验证AUC达0.803,联合临床-瘤内-瘤周影像组学模型训练AUC为0.863,校准良好且SHAP分析提升了可解释性。

要点

  • CA125和肿瘤直径是淋巴血管间隙侵犯的独立危险因素。
  • 神经网络模型在六种算法中验证AUC最高,达0.803。
  • 联合临床-瘤内-瘤周影像组学模型具有良好净临床获益,阈值范围0.1-0.7。

核心结论

  • NeuralNetwork模型在六种机器学习算法中预测子宫内膜癌淋巴血管间隙侵犯表现最优。
  • 联合临床-瘤内-瘤周影像组学模型结合SHAP可视化工具可无创术前预测淋巴血管间隙侵犯。

研究设计与样本

  • 回顾性研究,两中心共纳入408例子宫内膜癌患者,均行术前多参数MRI。
  • 按医院划分训练集和验证集,比较六种机器学习算法并构建五个附加模型。
  • 通过AUC、校准曲线和决策曲线分析评估模型性能。

诊断标准与关键数值

  • Logistic回归确定CA125和肿瘤直径为淋巴血管间隙侵犯的独立风险因素。
  • NeuralNetwork模型验证AUC为0.803。
  • 联合临床-瘤内-瘤周影像组学模型训练AUC为0.863,验证AUC为0.803。
  • Hosmer-Lemeshow检验P值大于0.05,提示模型校准良好。
  • 决策曲线分析显示在阈值0.1-0.7范围内具有良好净临床获益。

临床应用与阅片要点

  • 术前MRI影像组学特征联合CA125和肿瘤直径可用于无创预测子宫内膜癌淋巴血管间隙侵犯。
  • SHAP可视化工具可帮助理解各特征对模型预测结果的贡献。

局限性

  • 回顾性研究设计,存在选择偏倚的可能。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

RATIONALE AND OBJECTIVES: To develop and validate a machine learning model combining multiparametric Magnetic Resonance Imaging (MRI) radiomics and clinical indicators for predicting lymphovascular space invasion (LVSI) in endometrial cancer (EC).

MATERIALS AND METHODS: This retrospective study enrolled EC patients who underwent preoperative MRI at two centers. Of 567 initially screened patients, 408 were included per inclusion/exclusion criteria, divided into training and validation sets by hospital. Clinical risk factors and intratumoral/peritumoral radiomic features were identified. Six machine learning algorithms were used to build models; the one with the highest validation Area Under the Curve (AUC) was optimal. Five additional models were developed, and performance was evaluated via AUC, calibration curves, and decision curve analysis (DCA).

RESULTS: Logistic regression identified CA125 and tumor diameter as independent LVSI risk factors. Six machine learning models were built with CA125, tumor diameter, Rad_Score1 and Rad_Score2; the NeuralNetwork performed best (validation AUC=0.803). The combined clinical-intratumoral-peritumoral radiomics model achieved the highest AUC(training AUC = 0.863, validation AUC = 0.803), with good calibration (Hosmer-Lemeshow test, P > 0.05) and favorable net clinical benefit (threshold 0.1-0.7). SHapley Additive exPlanations (SHAP) analysis enhanced model interpretability.

CONCLUSION: This study systematically compared the predictive performance of six machine learning models for LVSI in EC, identifying the NeuralNetwork model as the most optimal. The combined clinical-intratumoral-peritumoral radiomics model, alongside its SHAP visualization tool, enhanced the accuracy (ACC) of non-invasive preoperative LVSI prediction, demonstrating certain potential for clinical application.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Meng, Dou, Yin, et al. Multiparametric MRI Radiomics-Based Interpretable Machine Learning Model for the Prediction of Lymphovascular Space Invasion in Endometrial Cancer. Acad Radiol. 2026. PMID: 42476832. doi:10.1016/j.acra.2026.06.067

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。